skills.rest
AnderHonorato
AnderHonoratoCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

webdev-llm-integration

Integrates built-in LLM chat completions, structured JSON, and streaming into Manus webdev projects.

Updated Aug 28, 2026
Search Tags:#typescript#llm#streaming#trpc#json schema#model selection#chat completions
One-click install
npx skills add https://github.com/AnderHonorato/Mem-rias-IA---Infinity --skill webdev-llm-integration-anderhonorato
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: webdev-llm-integration
Source: https://github.com/AnderHonorato/Mem-rias-IA---Infinity/tree/main/Manus/Skills/webdev-llm-integration
Command: npx skills add https://github.com/AnderHonorato/Mem-rias-IA---Infinity --skill webdev-llm-integration-anderhonorato

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Adding AI features to a Manus webdev fullstack or Expo mobile project normally requires managing API keys, model selection, and response parsing manually. This Skill provides preconfigured server-side LLM helpers with platform-injected credentials, so no manual key setup is required. ## Core Features & Use Cases - Chat Completions: Call invokeLLM from server-side code (e.g., tRPC procedures) with system/user/assistant messages, including image and file content. - Structured JSON Responses: Enforce JSON Schema output via response_format for reliable data extraction tasks. - Model Discovery & Reasoning: List available models with listLLMModels and pass thinking/reasoning parameters for Claude, GPT-5, and Gemini families. - Use Case: Build an AI feature that extracts a name and age from user-submitted text by calling invokeLLM with a strict JSON schema inside a tRPC procedure, then render the markdown response with Streamdown. ## Quick Start Ask the AI to add an LLM-powered endpoint to your Manus webdev project using the invokeLLM helper from server/_core/llm with a structured JSON response.

Frequently Asked Questions about webdev-llm-integration

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I call an LLM from a Manus webdev project?▼

Import invokeLLM from ./server/_core/llm and call it with a messages array containing system and user roles. Always invoke it from server-side code such as tRPC procedures so credentials stay on the server and are never exposed to clients.

How to get structured JSON output from an LLM API?▼

Pass a response_format object with type json_schema and a strict schema defining properties, required fields, and additionalProperties false. The model returns JSON matching the schema, accessible via choices[0].message.content and parsed with JSON.parse.

Does invokeLLM support streaming responses?▼

All models support streaming, but invokeLLM does not expose a stream parameter by default. Modify the helper to pass stream true and parse the SSE response, listening on res close with a finished flag to avoid aborting the upstream.

How do I enable thinking or reasoning for Claude, GPT-5, or Gemini models?▼

Pass model-specific extension params: reasoning with effort levels for OpenAI gpt-5, thinking with type enabled and budget_tokens for Anthropic Claude, and thinking with budget_tokens for Google Gemini. Check capabilities.thinking_example from the models catalog for exact shapes.

How can I list available LLM models at runtime?▼

Call listLLMModels from ./server/_core/llm, which returns OpenAI-standard model metadata. Combine it with invokeLLM to discover model IDs dynamically instead of hardcoding them, for example finding an ID starting with claude-.

Related Skills

Explore More Software Engineering Skills→
Military-Veteran-Team-LPT-RealtyMilitary-Veteran-Team-LPT-Realty

webdev-llm-integration

Integrates built-in LLM chat completions, structured JSON, and reasoning into Manus webdev projects.

Official
Intermediate
TKlerxTKlerx

streamdown

Render streaming Markdown in React with syntax highlighting, Mermaid diagrams, and math.

Community
Advanced
githubnextgithubnext
5.1k

optimize-agentic-workflow

Analyze and reduce token consumption in GitHub Agentic Workflows using audit data.

Official
Intermediate
IbIFACE-TechIbIFACE-Tech

provider-integration

Configure and switch between multiple LLM providers like OpenAI, Anthropic, Azure, and Ollama.

Official
Intermediate